Triple
T6488453
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Acrisius |
E146572
|
entity |
| Predicate | orderedAction |
P568
|
FINISHED |
| Object | casting Danaë and Perseus into the sea |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: casting Danaë and Perseus into the sea | Statement: [Acrisius, orderedAction, casting Danaë and Perseus into the sea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: orderedAction Context triple: [Acrisius, orderedAction, casting Danaë and Perseus into the sea]
-
A.
orderedEvent
Indicates that one event occurs before another in a defined temporal or logical sequence.
-
B.
order
chosen
Indicates that one entity requests, arranges, or directs that another entity provide a good, service, or action, typically in a specified sequence or priority.
-
C.
orderAuthority
Indicates that one entity has the formal power or right to issue orders or directives to another entity.
-
D.
orderedSackOf
Indicates that one entity is a collection of items arranged in a specific sequence, where the order of elements in the sack matters.
-
E.
orderedProtectionBy
Indicates that one entity has formally requested or arranged protective measures to be provided by another entity.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69c0090158c08190af0df9a2348d2d52 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c06a97fff88190b6f993c14df62649 |
completed | March 22, 2026, 10:18 p.m. |
| PD | Predicate disambiguation | batch_69c06740bebc81909d9d6956baa2bcb9 |
completed | March 22, 2026, 10:03 p.m. |
Created at: March 22, 2026, 4:52 p.m.